Nonparametric estimation of conditional probability distributions using a generative approach based on conditional push-forward neural networks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Franco, Nicola Rares, Tedesco, Lorenzo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912781578534912
author Franco, Nicola Rares
Tedesco, Lorenzo
author_facet Franco, Nicola Rares
Tedesco, Lorenzo
contents We introduce conditional push-forward neural networks (CPFN), a generative framework for conditional distribution estimation. Instead of directly modeling the conditional density $f_{Y|X}$, CPFN learns a stochastic map $φ=φ(x,u)$ such that $φ(x,U)$ and $Y|X=x$ follow approximately the same law, with $U$ a suitable random vector of pre-defined latent variables. This enables efficient conditional sampling and straightforward estimation of conditional statistics through Monte Carlo methods. The model is trained via an objective function derived from a Kullback-Leibler formulation, without requiring invertibility or adversarial training. We establish a near-asymptotic consistency result and demonstrate experimentally that CPFN can achieve performance competitive with, or even superior to, state-of-the-art methods, including kernel estimators, tree-based algorithms, and popular deep learning techniques, all while remaining lightweight and easy to train.
format Preprint
id arxiv_https___arxiv_org_abs_2511_14455
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nonparametric estimation of conditional probability distributions using a generative approach based on conditional push-forward neural networks
Franco, Nicola Rares
Tedesco, Lorenzo
Machine Learning
Methodology
We introduce conditional push-forward neural networks (CPFN), a generative framework for conditional distribution estimation. Instead of directly modeling the conditional density $f_{Y|X}$, CPFN learns a stochastic map $φ=φ(x,u)$ such that $φ(x,U)$ and $Y|X=x$ follow approximately the same law, with $U$ a suitable random vector of pre-defined latent variables. This enables efficient conditional sampling and straightforward estimation of conditional statistics through Monte Carlo methods. The model is trained via an objective function derived from a Kullback-Leibler formulation, without requiring invertibility or adversarial training. We establish a near-asymptotic consistency result and demonstrate experimentally that CPFN can achieve performance competitive with, or even superior to, state-of-the-art methods, including kernel estimators, tree-based algorithms, and popular deep learning techniques, all while remaining lightweight and easy to train.
title Nonparametric estimation of conditional probability distributions using a generative approach based on conditional push-forward neural networks
topic Machine Learning
Methodology
url https://arxiv.org/abs/2511.14455